Triple

T22113321
Position Surface form Disambiguated ID Type / Status
Subject Cipatat E546471 entity
Predicate geographicRegion P285 FINISHED
Object Parahyangan NE NERFINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Parahyangan | Statement: [Cipatat, geographicRegion, Parahyangan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Parahyangan
Context triple: [Cipatat, geographicRegion, Parahyangan]
  • A. Parahyangan chosen
    Parahyangan is a highland cultural region in West Java, Indonesia, traditionally associated with Sundanese people and their distinct customs, language, and landscape.
  • B. Garut highlands
    The Garut highlands are a mountainous region in West Java, Indonesia, known for their cool climate, volcanic landscapes, tea plantations, and hot springs.
  • C. Sindangkerta
    Sindangkerta is a district-level area in West Java, Indonesia, situated within the administrative boundaries of West Bandung Regency.
  • D. Ciawi
    Ciawi is a district in West Java, Indonesia, known as a gateway area near Bogor that connects major routes toward Puncak and other highland tourist destinations.
  • E. Cianjur highlands
    The Cianjur highlands are a mountainous region in West Java, Indonesia, known for their cool climate, terraced agriculture, and scenic landscapes within the broader Parahyangan area.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69e11e38b3848190ac3a4fa97d56e65a completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f1294b9d5c8190897b760ca4f3b09a completed April 28, 2026, 9:40 p.m.
Created at: April 16, 2026, 8:31 p.m.